What this category's data looks like
This page addresses business basis queries in the scenario of safety grading and classification of university laboratories. The materials come from three types: the campus laboratory grading and classification table, the hazard source list, and the safety responsibility statement. The grading and classification table records the laboratory name, room number, hazard level, grading basis clause, and effective date; the hazard source list records the hazard source name, category, quantity, storage location, and update date; the safety responsibility statement records the responsible person, scope of responsibility, signature, and receipt date. The materials are updated according to the academic year or special inspection cadence. The same laboratory often appears repeatedly in the grading and classification table and the hazard source list, and the field names, quantities, dates, and signature statuses need to be compared item by item. After the three types of materials enter the parsing and training tasks, each becomes an independent data row, allowing the retrieval layer to trace back to the original text by basis clause.
Configuration and implementation checks
This step is executed by the parsing and training tasks (server-side tasks), outputting data rows and index statuses (parsed, indexing, indexed). The basis clauses that can be traced back to the original text are then completed by retrieval and subsequent processing.
| Object | Check | Verification action |
|---|---|---|
| Laboratory grading and classification table | The fields include laboratory name, room number, hazard level, grading basis clause, effective date, and signature, and the name, quantity, and date need to be aligned item by item with the hazard source list | Open the data row to check whether the status is parsed / indexing / indexed, and check whether the chunks corresponding to chunkSize and chunkSplitter cover the grading basis clause |
| Hazard source list | The fields include hazard source name, category, quantity, storage location, and update date, and the name, quantity, and date of the same record need to be checked against the grading and classification table for consistency | Check the identifiers of the file record and the data row separately, and confirm that the same hazard source falls into different data rows in the two materials and can be traced back to the original text |
| Safety responsibility statement | The fields include responsible person, scope of responsibility, signature, and receipt date, and it is necessary to check whether the signature and receipt are complete and whether the version is current | Check whether the data rows covered by the rebuild task fall only on data with completed indexing, and confirm that the processing mode corresponding to trainingType matches the current materials |
| Data row index status | It is in one of the three states and consistent with the interface display, and data pending indexing does not participate in recall | Open the data row to check the status, and confirm that the rebuild scope covers only data with completed indexing |
Three common errors
- Symptom: The name and quantity of the same laboratory do not match between the grading and classification table and the hazard source list. Cause: The two materials are entered separately, lacking cross-material field comparison and a unified identifier.
- Symptom: The responsibility statement still uses an old version, and the signature or receipt is missing. Cause: The version is not synchronized, the update cadence is out of step with the special inspection timing, and the signature status is not updated with the materials.
- Symptom: Newly uploaded materials cannot be found. Cause: Successful parsing does not equal a retrieval hit; the data row is still in parsed or indexing and has not entered the completed indexing state.
How to verify the setup
Acceptance for this feature: upload one material and observe the data row status transitions and the coverage scope of the rebuild task.
Business test: ask a cross-material basis question and see whether the answer provides a traceable source.
- Open the data row to check whether the status is parsed / indexing / indexed, and check the identifiers of the file record and the data row separately.
- Check whether the data rows covered by the rebuild task fall only on data with completed indexing, and verify whether
chunkSize,chunkSplitter, andtrainingTypematch the current materials.